diff options
author | Jesús <heckyel@hyperbola.info> | 2021-06-09 17:54:27 -0500 |
---|---|---|
committer | Jesús <heckyel@hyperbola.info> | 2021-06-09 17:54:27 -0500 |
commit | 27fe903c511691c078942bef5ee9a05a43b15c8f (patch) | |
tree | 50f30ab2ec749b965869518c0a28651f8677f0d3 /hypervideo_dl/extractor/dbtv.py | |
download | hypervideo-27fe903c511691c078942bef5ee9a05a43b15c8f.tar.lz hypervideo-27fe903c511691c078942bef5ee9a05a43b15c8f.tar.xz hypervideo-27fe903c511691c078942bef5ee9a05a43b15c8f.zip |
initial
Diffstat (limited to 'hypervideo_dl/extractor/dbtv.py')
-rw-r--r-- | hypervideo_dl/extractor/dbtv.py | 57 |
1 files changed, 57 insertions, 0 deletions
diff --git a/hypervideo_dl/extractor/dbtv.py b/hypervideo_dl/extractor/dbtv.py new file mode 100644 index 0000000..aaedf2e --- /dev/null +++ b/hypervideo_dl/extractor/dbtv.py @@ -0,0 +1,57 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class DBTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?dagbladet\.no/video/(?:(?:embed|(?P<display_id>[^/]+))/)?(?P<id>[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8})' + _TESTS = [{ + 'url': 'https://www.dagbladet.no/video/PynxJnNWChE/', + 'md5': 'b8f850ba1860adbda668d367f9b77699', + 'info_dict': { + 'id': 'PynxJnNWChE', + 'ext': 'mp4', + 'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen', + 'description': 'md5:49cc8370e7d66e8a2ef15c3b4631fd3f', + 'thumbnail': r're:https?://.*\.jpg', + 'upload_date': '20160916', + 'duration': 69, + 'uploader_id': 'UCk5pvsyZJoYJBd7_oFPTlRQ', + 'uploader': 'Dagbladet', + }, + 'add_ie': ['Youtube'] + }, { + 'url': 'https://www.dagbladet.no/video/embed/xlGmyIeN9Jo/?autoplay=false', + 'only_matching': True, + }, { + 'url': 'https://www.dagbladet.no/video/truer-iran-bor-passe-dere/PalfB2Cw', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return [url for _, url in re.findall( + r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?dagbladet\.no/video/embed/(?:[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8}).*?)\1', + webpage)] + + def _real_extract(self, url): + display_id, video_id = re.match(self._VALID_URL, url).groups() + info = { + '_type': 'url_transparent', + 'id': video_id, + 'display_id': display_id, + } + if len(video_id) == 11: + info.update({ + 'url': video_id, + 'ie_key': 'Youtube', + }) + else: + info.update({ + 'url': 'jwplatform:' + video_id, + 'ie_key': 'JWPlatform', + }) + return info |